pn-a2a-interop

pn-a2a-interop is a skill for Cursor from perniemann/pnCore. It costs 87 tokens per session (2,177 once invoked), scanned A, original, MIT.

A guide to the Agent2Agent Protocol, a standard way for AI agents built with different systems or owned by different organizations to advertise abilities and exchange tasks. It covers service descriptions, task routing, authentication, and audit records.

In plain words
What is it for?
Use it to connect agents from systems such as LangGraph, ADK, CrewAI, or AutoGen, including HTTP task handling, streaming results, trust checks, and capability negotiation.
Why use it?
It helps avoid custom integrations for every pair of agents and clarifies how agents can discover one another, agree on capabilities, and communicate safely.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the pn-core plugin — 133 skills, 19 commands, 9 agents, 1 MCP server shipped together

Good fit Use it to connect agents from systems such as LangGraph, ADK, CrewAI, or AutoGen, including HTTP task handling, streaming results, trust checks, and capability negotiation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/perniemann/pncore/pn-a2a-interop
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add perniemann/pnCore --skill pn-a2a-interop
Clone the repo
git clone --depth 1 https://github.com/perniemann/pnCore

Made for: Cursor.

Or install pn-core, the plugin that ships this one along with the rest of its 133 skills, 19 commands, 9 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pn-a2a-interop

README.md
[![agentmods](https://agentmods.dev/badge/skills/perniemann/pncore/pn-a2a-interop/github.svg)](https://agentmods.dev/skills/perniemann/pncore/pn-a2a-interop)
Your own site
<a href="https://agentmods.dev/skills/perniemann/pncore/pn-a2a-interop"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-a2a-interop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pn-a2a-interop

Your own site · 80×15
<a href="https://agentmods.dev/skills/perniemann/pncore/pn-a2a-interop"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-a2a-interop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,177 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.02177
Opus 5 $0.00044 $0.01089
Sonnet 5 $0.00017 $0.00435
Haiku 4.5 $0.00009 $0.00218

Measured 6d ago against content hash f62246d177fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pn-a2a-interop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/pn-core-mcp/content/skills/integrations/pn-a2a-interop/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A2A Interoperability Skill

When used as a standalone skill, begin every response with [pn-skill] 🔺

When to use

  • Connecting a pnCore-orchestrated agent to an external agent from a different framework or organization
  • Designing a multi-agent system where specialist agents run independently (not all inside pnCore)
  • Implementing or consuming an A2A-compliant service (well-known endpoint, Agent Card, task routing)
  • Composing agents across an enterprise value chain (e.g. manufacturer ↔ supplier, retailer ↔ logistics)
  • Auditing or adding inter-agent trust, authentication, or payment (Agent Payments Protocol / AP2)

Background

The Agent2Agent (A2A) Protocol (Google, 2025) standardizes how agents advertise capabilities and exchange tasks across framework and ownership boundaries. An agent exposes an Agent Card at /.well-known/agent.json, accepts tasks via HTTP POST, streams results via SSE, and negotiates input/output MIME types.

Key concepts:

Concept Description
Agent Card JSON descriptor at /.well-known/agent.json — name, description, capabilities, skills, auth, endpoints
Task The unit of work: { id, message, sessionId?, metadata? }
Part A typed content fragment in a message: TextPart, FilePart, DataPart
Artifact Task output; same Part types; streamed or returned on completion
Push notification Webhook callback for long-running tasks when client cannot poll
AP2 Agent Payments Protocol — agent-to-agent payment initiation/settlement

Instructions

1. Discover the remote agent

GET https://<remote-agent-host>/.well-known/agent.json

Parse the Agent Card and extract:

  • skills[] — what the agent can do; match against your task requirements
  • authenticationnone, apiKey, oauth2, mtls
  • defaultInputModes / defaultOutputModes — negotiate MIME types
  • capabilities.streaming — SSE support
  • capabilities.pushNotifications — push support

Read the full file on GitHub · 209 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 209 lines · 87 tokens per session scan A f62246d177fe

Subscribe to this mod's changes

pn-a2a-interop is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 3d ago), licensed MIT. It adds 87 tokens to every session and 2,177 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

architecture-patterns

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or…

wshobson/agents · 65 tokens

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens

chat-sdk

Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI…

vercel-labs/open-agents · 191 tokens

developing-genkit-tooling

Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency guidelines.

genkit-ai/genkit · 35 tokens

ax-go-flow

Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.

ax-llm/ax · 43 tokens

output-dev-workflow-cost

Calculate and display the cost of an Output SDK workflow execution run. Use when checking LLM token costs, API service costs, or total spend for a specific workflow run.

growthxai/output · 40 tokens